Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real operational context annotations cannot convey: the synthetic fallback when no request is passed, the permission requirement, and the important caveat that rights_confirmed=true is an attestation and 'does not verify a licence'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core action before the fallback and the rights caveat. Slight ambiguity in 'require permission' as a directive, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output structure is covered by the output schema, and the permission/fallback rules are stated, which is what a complex replay tool most needs. However, given a nine-field required nested request at 0% schema coverage, the description leaves an agent guessing about data_mode semantics, valid date-window rules, and how positions/prices must correspond.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, but it only touches two things: the optionality of 'request' and the meaning of rights_confirmed. The large nested ReplayRequest (as_of, nav, prices, measure, proxies, data_mode, start/end, positions) is left entirely to property names, and notably data_mode is not explained relative to the omit-request shortcut.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Replay') tied to a concrete resource ('a dated historical window') and scope ('from the caller's own price levels on linear positions'). It does not name or differentiate itself from siblings like risk_backtest or risk_stress, but the replay-of-historical-window framing is distinct enough to select on.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit branch: omit the request to get the shipped synthetic example, otherwise supply data and permission. What is missing is guidance on when to prefer this over the related stress/backtest tools, and no exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.